Librarian Bot: Add base_model information to model
Browse filesThis pull request aims to enrich the metadata of your model by adding [`braindao/flan-t5-cnn`](https://huggingface.co/braindao/flan-t5-cnn) as a `base_model` field, situated in the `YAML` block of your model's `README.md`.
How did we find this information? We extracted this infromation from the `adapter_config.json` file of your model.
**Why add this?** Enhancing your model's metadata in this way:
- **Boosts Discoverability** - It becomes straightforward to trace the relationships between various models on the Hugging Face Hub.
- **Highlights Impact** - It showcases the contributions and influences different models have within the community.
For a hands-on example of how such metadata can play a pivotal role in mapping model connections, take a look at [librarian-bots/base_model_explorer](https://huggingface.co/spaces/librarian-bots/base_model_explorer).
This PR comes courtesy of [Librarian Bot](https://huggingface.co/librarian-bot). If you have any feedback, queries, or need assistance, please don't hesitate to reach out to [@davanstrien](https://huggingface.co/davanstrien).
If you want to automatically add `base_model` metadata to more of your modes you can use the [Librarian Bot](https://huggingface.co/librarian-bot) [Metadata Request Service](https://huggingface.co/spaces/librarian-bots/metadata_request_service)!
@@ -1,32 +1,29 @@
|
|
1 |
---
|
2 |
-
license: mit
|
3 |
-
library_name: peft
|
4 |
-
datasets:
|
5 |
-
- samsum
|
6 |
language:
|
7 |
- en
|
|
|
|
|
8 |
tags:
|
9 |
- summarization
|
10 |
- text-generation
|
11 |
- toxicity-reduction
|
12 |
- reinforcement-learning
|
|
|
|
|
13 |
widget:
|
14 |
-
- text:
|
15 |
-
|
16 |
-
|
17 |
-
up
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
-
|
22 |
-
have to see my supervisor on Monday <unk> Kai: not too long a break Kate:
|
23 |
-
Still better than nothing. Summary:
|
24 |
example_title: Summarization Example 1
|
25 |
-
- text:
|
26 |
-
|
27 |
-
|
28 |
-
|
29 |
-
Chinese from TaoTao for dinner Scott: now we have a suspect Summary:
|
30 |
example_title: Summarization Example 2
|
31 |
pipeline_tag: text2text-generation
|
32 |
inference:
|
@@ -39,6 +36,7 @@ inference:
|
|
39 |
no_repeat_ngram_size: 2
|
40 |
num_return_sequences: 1
|
41 |
do_sample: true
|
|
|
42 |
---
|
43 |
|
44 |
# Flan-T5 (base-sized) Dialogue Summarization with reduced toxicity using RLAIF
|
|
|
1 |
---
|
|
|
|
|
|
|
|
|
2 |
language:
|
3 |
- en
|
4 |
+
license: mit
|
5 |
+
library_name: peft
|
6 |
tags:
|
7 |
- summarization
|
8 |
- text-generation
|
9 |
- toxicity-reduction
|
10 |
- reinforcement-learning
|
11 |
+
datasets:
|
12 |
+
- samsum
|
13 |
widget:
|
14 |
+
- text: 'Summarize the following Conversation: Kate: Good morning. Kai: Hi! How official!
|
15 |
+
Kate: I wrote it at 4am Kai: I''ve noticed. Why? Kate: I had to get up early to
|
16 |
+
catch the bus to the airport Kai: Where are you flying? Kate: To Antwerp! I''m
|
17 |
+
fed up with Cambridge Kai: poor thing. Why? Kate: Just a stupid, elitist place
|
18 |
+
without a soul. Or with a soul made of money. Kai: Try to rest a bit in Belgium,
|
19 |
+
do not work too much. Kate: I have to work, but at least not in this soulless
|
20 |
+
place. Kai: When are you coming back? Kate: I have to see my supervisor on Monday
|
21 |
+
<unk> Kai: not too long a break Kate: Still better than nothing. Summary:'
|
|
|
|
|
22 |
example_title: Summarization Example 1
|
23 |
+
- text: 'Summarize the following Conversation: Dean: I feel sick Scott: hungover?
|
24 |
+
Dean: no, like I ate something bad Scott: what did you eat yesterday? Dean: breakfast
|
25 |
+
at Coffee Lovers'' Scott: this is a rather safe place Dean: and Chinese from TaoTao
|
26 |
+
for dinner Scott: now we have a suspect Summary:'
|
|
|
27 |
example_title: Summarization Example 2
|
28 |
pipeline_tag: text2text-generation
|
29 |
inference:
|
|
|
36 |
no_repeat_ngram_size: 2
|
37 |
num_return_sequences: 1
|
38 |
do_sample: true
|
39 |
+
base_model: braindao/flan-t5-cnn
|
40 |
---
|
41 |
|
42 |
# Flan-T5 (base-sized) Dialogue Summarization with reduced toxicity using RLAIF
|